search_code

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds a useful nuance ('lazy class-file metadata', 'real string constants'), but it does not state whether the tool is read-only, how it resolves JARs, what mode does, how results are returned, or how limits apply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense sentence with no redundancy or filler. It front-loads the core purpose and avoids repeating information already available in annotations or the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 10 parameters, multiple sibling tools, and no output schema or annotations, the one-sentence description is not enough for an agent to reliably select and invoke this tool. Missing pieces include selector prioritization, mode semantics, output format expectations, and practical differences from sibling search tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description clarifies the semantic intent behind the kind enum by naming methods, fields, annotations, references, and strings. Since schema coverage is 60%, the schema already documents several parameters; the description adds some meaning but does not explain the required query/kind relationship or the behavior of mode, limit, and format.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Find') and a distinct resource scope: method/field declarations, annotations, references, and string constants in class-file metadata. It does not explicitly differentiate itself from siblings like search_class or inspect_jar, but the focus on multiple code-search entity kinds is reasonably distinctive.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as search_class, find_implementations, or inspect_jar. It also does not explain which JAR-selector parameter is preferred or what conditions would make one selector better than another.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.